플러그인
DeepSeek-Harness 플러그인을 찾아보고, 필터링하고, 설치하세요.
플러그인 98개 찾음
dsh-plugin-zoom
drliuhuan/dsh-plugin-zoom
설정 항목, Ctrl+휠 또는 세션 헤더 컨트롤로 Harness Web UI를 75%~200% 확대·축소하며, 고DPI 화면에서도 글자가 선명하고 읽기 쉽도록 합니다.
dsh-ui-scale
juliankang4/dsh-ui-scale
Settings - General에서 slider, 퍼센트 입력란 또는 preset으로 DeepSeek Harness 전체를 50%~200% 확대/축소합니다. 메뉴와 popup도 포함합니다. 자체 zoom이 없는 dsh web과 desktop 앱에서 작동합니다.
dsh-page-zoom
centaurea5547196/dsh-page-zoom
DSH Web UI 페이지 확대/축소 기능입니다. Ctrl+마우스 휠로 전체 인터페이스를 5% 단위(30%~200%)로 조절하고 확대율을 로컬에 기억합니다. 오른쪽 아래에 배율이 표시된 돋보기를 보여줍니다.
dsh-diagram
zhangtell/dsh-diagram
대화의 Mermaid 코드 블록을 다이어그램으로 표시합니다(플로차트, 시퀀스, 클래스, 상태, ER, 간트, 파이). 확대/축소, 소스 전환, PNG 복사, SVG 다운로드를 지원합니다.
dsh-mermaid-smooth
gitbytefree/dsh-mermaid-smooth
dsh Web 채팅의 Mermaid 코드 펜스를 기본적으로 SVG 다이어그램으로 렌더링합니다. 커서 기준으로 부드럽게 확대/이동하고 펜스별 다이어그램/코드 전환 상태를 `localStorage`에 저장합니다. 다크 모드를 따르며 오프라인 엔진을 포함합니다.
dsh-theme-whalegirl
zhoucourier/dsh-theme-whalegirl
DSH Web UI용 Whale Girl 라이트 테마입니다. DreamSkin 스킨 패키지를 포팅하고 네이티브 --dsw-* 토큰을 전면 재매핑합니다. 작품 이미지를 하나의 밝은 종이 레이어 뒤의 배경으로 배치합니다. 유리 효과 강도, 대화에만 종이 배경 적용, 배경의 베일/초점/확대, 작성창 포커스 광채를 실시간 조절하며 설치된 패키지 페이지에 이중 언어 설정 폼이 있습니다. 비주얼 계보: 溟月 by 上善无形 → DeepSeek maid ver. by ZipZipPipe. 작품 CC BY-NC-SA 4.0, 코드 MIT.
dsh-desktop-kit
mdr-ex1000/dsh-desktop-kit
DSH 웹 UI용 macOS 데스크톱 셸: 루프백 웹 서페이스 위의 작은 Tauri/WKWebView 윈도우와 함께하는 플러그인 — 실제 macOS 전체 화면, 단일 인스턴스, 외부 링크는 시스템 브라우저로 위임, 브라우저 스타일 줌.
dsh-bridge-preview
xing666173/dsh-bridge-preview
텍스트 전용 모델에서 dsh-tool-vision으로 브리지된 붙여넣기 이미지에 대한 채팅 내 인라인 이미지 미리보기 (클릭하면 확대, 이전 메시지에도 미리보기 적용).
dsh-mermaid-render
genius-alray/dsh-mermaid-render
웹 UI 대화용 Mermaid 다이어그램 렌더러: mermaid 코드 블록을 대화형 카드(확대, 너비 맞춤, 전체 화면 뷰어, 미리보기/코드 전환)로 렌더링하며 공식 UI 프리미티브를 사용합니다. 렌더링에 실패하면 원래 코드 블록을 유지하고 인라인 오류 배너를 표시합니다.
plot3d-surface
suzunami/plot3d-surface
Interactive 3D surface plotting tool card for the DSH chat, with drag-rotate, wheel-zoom and live-editable expression, range and mesh.
dsh-english-lit-reader
yubococo/dsh-english-lit-reader
English paper reader inside DeepSeek Harness: drag in a PDF and select a sentence to get its translation in the card column beside the page, with the model called only when you press Translate. Produces a six-section Chinese analysis (overview, problem and prior methods, technical approach, experimental setup and results, limitations, reproducibility), reading the whole paper in one call when the selected model can fit it and otherwise taking complete excerpt notes first. Resolves the bibliography in three stages: the original entries appear immediately, then Chinese titles, then links found through Crossref and OpenAlex, where a DOI or arXiv id printed in the entry is used directly, "not found" is written instead of a guessed link, and rate-limited lookups are reported separately as temporarily failed with a retry. Explains a selected figure together with its nearby caption when the model accepts images, typesets and explains a formula through KaTeX, explains a selected term against its own sentence and the paper text and keeps it as a glossary entry, records highlights and annotations as two independent kinds that do not overwrite each other, and searches inside the document. Nine interface tones (four light, five dark) plus seven paper colours are applied as a darken-blended layer above the page canvas, so only the white sheet is recoloured and text, figures and tables keep their own colours. Function cards can be reordered, detached and resized; one, two and three page layouts, zoom with Ctrl+wheel, two-way panning, fullscreen, and a per-paper recent list kept in IndexedDB. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-drawcraft
vhow123/dsh-drawcraft
Drawcraft — an image-generation studio in the sidebar panel list, split into three pages that share one result. Prompt page: pick a target dialect, a style and an aspect, write one rough sentence, and a chat model returns an 11-field shot breakdown that the plugin stitches into the syntax that dialect actually accepts — six dialects (natural English, natural Chinese, GPT-Image, Midjourney, Stable Diffusion, nano-banana), 18 style presets, negative prompts, filler-word stripping and local history; an image can also be reverse-engineered into the same fields, and a one-line edit such as light turns to dusk rewrites only the named fields. Image page: text-to-image and image-to-image through a locally installed image-generation plugin or through an OpenAI-compatible endpoint you add in the panel, whose key stays on disk and is never echoed back to the browser; with a subject image attached it posts to /images/edits and carries up to four extra references. Canvas page: an infinite canvas where image, prompt and result nodes are dragged, resized, wired by hand or by generation, with undo and redo, marquee selection, copy and paste, a minimap, pointer-centred wheel zoom and JSON export and import; rendering from a node walks the whole upstream chain so no reference is dropped, one node can be pinned as the subject, and the reference library opens inside the canvas. A reference library of 4,345 Chinese-labelled entries — 1,439 poses with matching depth maps, 1,407 outfits, 1,499 portraits — is searched and faceted by pose system, angle, category, season, hair length and hairstyle, paged 24 at a time, and the entries you pick are injected into the prompt as binding constraints. Renders can pick the image channel and model, one of eight aspect sizes or follow-the-aspect, and quality at 1K/2K/4K; a preview opens into a lightbox with pointer-centred wheel zoom from 20% to 800%, drag-to-pan, double-click reset and one-click save. The prompt tools and the library are also exposed as the optimize_image_prompt, patch_image_prompt and search_reference_gallery agent tools. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-handy-toolkits
kuoxinxin/dsh-handy-toolkits
Three GUI toolkits in one bundle: whole-page zoom (Cmd/Ctrl + Shift + =, - and 0, with a coordinate shim so anchored menus stay on their buttons), copy-on-select in the chat transcript (copies the dragged text and tells you how many characters, with an execCommand fallback), and Mermaid fences in replies drawn as diagrams with a full-screen viewer (wheel zoom anchored at the pointer, drag to pan) and PNG, SVG or source copy. The Mermaid engine ships inside the bundle, so nothing is fetched at runtime.
dsh-image-gen
adithyanraj03/dsh-image-gen
Multi-provider image generation and editing for DeepSeek Harness (OpenAI-compatible relays with custom /v1/images/generations endpoints, Gemini, Seedream, DashScope, Grok, GLM, local ComfyUI, subscription accounts), an Excalidraw MIT infinite-canvas studio with click-to-place and selection-to-edit references, and a pro viewer with zoom/pan/pinch, region notes and a markup mode that bakes marks into the pixels and sends normalized coordinates to the model.
dsh-preview-image
vfvrpq/dsh-preview-image
Image preview with real zoom, pan, rotation and full screen in the right-Sidebar document preview and the conversation lightbox.
dsh-dingpan
mumu1001ai-jpg/dsh-dingpan
A watchlist panel for A-share, Hong Kong, US, Korean and FTSE China A50 quotes, with daily/weekly/monthly candlestick charts that page and zoom, a global-markets board, sector boards, DRAM/NAND spot prices, and a draggable Windows taskbar price pill. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-lego-io-preview
youngharmony/dsh-lego-io-preview
3D preview for BrickLink Studio .io LEGO models in the DSH sidebar: orbit and zoom the real LDraw geometry, see the part count, and load parts missing from the bundled set from a local Studio install on demand. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-plugin-mermaid-markdown
sangaizhi/dsh-plugin-mermaid-markdown
Renders mermaid code blocks inside Markdown files as diagrams in the workspace file preview, with click-to-enlarge zoom.
dsh-r-runner
seally-web/dsh-r-runner
R in the sidebar: an RStudio-shaped workbench backed by a persistent R session over a loopback driver (6-9 s cold boot, then 12-84 ms per run). R syntax highlighting with a multi-buffer editor, file tree with extra folder mounts, environment pane you can edit in place, plot gallery with a floating viewer (zoom, resize, open original), five bottom tabs (console with prompt, persistent history, ?topic help, sortable data viewer, package manager with install.packages), completion / diagnostics / go-to-definition, .Rmd chunk runs, Rmd, Quarto and Shiny previews, and an agent-facing r_run tool. Requires a local R installation. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-prompt-forge
vhow123/dsh-prompt-forge
Image-generation prompt workshop in the sidebar panel list, working in four directions that share one result. Idea to prompt: pick a target dialect, a style and an aspect, write one rough sentence, and a chat model returns an 11-field shot breakdown that the plugin stitches into the syntax that dialect actually accepts — six dialects (natural English, natural Chinese, GPT-Image, Midjourney, Stable Diffusion, nano-banana), 18 style presets, negative prompts, filler-word stripping and local history. Image to prompt: drop a reference image and a vision model reverse-engineers the same fields. Prompt to prompt: type one line such as light turns to dusk and only the named fields are rewritten, everything else is copied verbatim. Prompt to image: the result card, or the panel itself before any optimization has run, renders through a locally installed image-generation plugin or through an OpenAI-compatible endpoint you add in the panel, whose key stays on disk and is never echoed back to the browser; with a main image attached it posts to /images/edits and carries up to four extra references, with only text it posts to /images/generations. A reference library of 4,345 Chinese-labelled entries — 1,439 poses with matching depth maps, 1,407 outfits, 1,499 portraits — is searched and faceted by pose system, angle, category, season, hair length and hairstyle, paged 24 at a time, and the entries you pick are injected into the prompt as binding constraints. Renders can pick the image channel and model, one of eight aspect sizes or follow-the-aspect, and quality at 1K/2K/4K; a preview opens into a lightbox with pointer-centred wheel zoom from 20% to 800%, drag-to-pan, double-click reset and one-click save. The first two directions and the library are also exposed as the optimize_image_prompt, patch_image_prompt and search_reference_gallery agent tools. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-screenshot
joythatway/dsh-screenshot
Composer screenshot menu with three modes (region capture that hides the harness window, a window list with live hover previews, and full screen); captures land in the draft or save to disk, the preview zooms with the mouse wheel, and a settings page changes the shortcut, save folder and auto-hide behaviour.
dsh-d2-diagrams
korioncn/dsh-d2-diagrams
Previews D2 diagrams in the DSH sidebar using the local D2 CLI, with live rendering, source editing, zoom, and chart, code, or split views.
dsh-memory-cloud
faruzancn/dsh-memory-cloud
Visualizes all DSH session memories as an interactive 3D nebula, with a neuron-signal skin, memory-scaled clusters, zoom-driven detail levels and a live write/read activity stream over SSE.
dsh-image-scope
olivine13/dsh-image-scope
Adds a pixel-coordinate viewer to the sidebar image preview: hover coordinates, one adjustable dashed rectangle with start/end/size labels, edge snapping, and true-pixel measurements across zoom.